Skip to content

Conversation

@YufengShi-dudu
Copy link
Collaborator

@YufengShi-dudu YufengShi-dudu commented Jul 15, 2025

  • Add support for passing transform_passes to VgfPipeline
  • Fix the vgf quantization
    • Enable Vgf quantization in ArmTester using VgfQuantizer.
    • Use tosa_version to distinguish between quantized and
      non-quantized paths instead of quant_stage, which may be
      None even under INT profile.

Change-Id: Id289ecbde57556e749c0a281ce6c8a000bb6eece

cc @digantdesai @freddan80 @per @zingo @oscarandersson8218

@YufengShi-dudu YufengShi-dudu added partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm ciflow/trunk release notes: arm Changes to the ARM backend delegate labels Jul 15, 2025
@pytorch-bot
Copy link

pytorch-bot bot commented Jul 15, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12484

Note: Links to docs will display an error until the docs builds have been completed.

❌ 1 New Failure, 1 Unrelated Failure

As of commit b3e6141 with merge base 07c8f0f (image):

NEW FAILURE - The following job has failed:

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Jul 15, 2025
@AdrianLundell
Copy link
Collaborator

Hi, could you update the description of the fix for the vgf quantization workflow to be more descriptive? Looks good otherwise!

- Add support for passing transform_passes to VgfPipeline
- Fix the vgf quantization
    - Enable Vgf quantization in ArmTester using VgfQuantizer.
    - Use tosa_version to distinguish between quantized and
      non-quantized paths instead of quant_stage, which may be
      None even under INT profile.

Change-Id: Id289ecbde57556e749c0a281ce6c8a000bb6eece
@YufengShi-dudu YufengShi-dudu force-pushed the extend-vgf-test-infra branch from 07fbb94 to 1210018 Compare July 16, 2025 14:10
@YufengShi-dudu
Copy link
Collaborator Author

Hey Adrian, could you review this patch again? Thanks!

@AdrianLundell AdrianLundell merged commit 84fed2f into pytorch:main Jul 17, 2025
198 of 200 checks passed
@AdrianLundell
Copy link
Collaborator

Failure not related

lucylq pushed a commit that referenced this pull request Jul 17, 2025
- Add support for passing transform_passes to VgfPipeline
- Fix the vgf quantization
    - Enable Vgf quantization in ArmTester using VgfQuantizer.
    - Use tosa_version to distinguish between quantized and
      non-quantized paths instead of quant_stage, which may be
      None even under INT profile.

Change-Id: Id289ecbde57556e749c0a281ce6c8a000bb6eece
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ciflow/trunk CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. partner: arm For backend delegation, kernels, demo, etc. from the 3rd-party partner, Arm release notes: arm Changes to the ARM backend delegate

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants